Poetic Meter Classification Using i-Vector-MTF Fusion

In this paper, a deep neural network (DNN)-based poetic meter classification scheme is proposed using a fusion of musical texture features (MTF) and i-vectors. The experiment is performed in two phases. Initially, the mel-frequency cepstral coefficient (MFCC) features are fused with MTF and classification is done using DNN. MTF include timbral, rhythmic, and melodic features. Later, in the second phase, the MTF is fused with i-vectors and classification is performed. The performance is evaluated using a newly created poetic corpus in Malayalam, one of the prominent languages in India. While the MFCCMTF/DNN system reports an overall accuracy of 80.83%, the ivector/MTF fusion reports an overall accuracy of 86.66%. The performance is also compared with a baseline support vector machine (SVM)-based classifier. The results show that the architectural choice of i-vector fusion with MTF on DNN has merit in recognizing meters from recited poems.

[1]  Rajeev Rajan,et al.  Poetic Meter Classification Using Acoustic Cues , 2018, 2018 International Conference on Signal Processing and Communications (SPCOM).

[2]  Jakob Uszkoreit,et al.  “Poetic” Statistical Machine Translation: Rhyme and Meter , 2010, EMNLP.

[3]  Patrick Kenny,et al.  Eigenvoice modeling with sparse training data , 2005, IEEE Transactions on Speech and Audio Processing.

[4]  José Fornari,et al.  Multi-Feature Modeling of Pulse Clarity: Design, Validation and Optimization , 2008, ISMIR.

[5]  George Tzanetakis,et al.  Musical genre classification of audio signals , 2002, IEEE Trans. Speech Audio Process..

[6]  Mathias Scharinger,et al.  Poetic speech melody: A crucial link between music and language , 2018, PloS one.

[7]  Shrikanth S. Narayanan,et al.  An Overview on Perceptually Motivated Audio Indexing and Classification , 2013, Proceedings of the IEEE.

[8]  Rui Pedro Paiva,et al.  Musical Texture and Expressivity Features for Music Emotion Recognition , 2018, ISMIR.

[9]  Kevin Knight,et al.  Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation , 2010, EMNLP.

[10]  Jean-François Bonastre,et al.  ALIZE, a free toolkit for speaker recognition , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[11]  Petri Toiviainen,et al.  A Matlab Toolbox for Music Information Retrieval , 2007, GfKl.

[12]  Farbod Razzazi,et al.  Automatic meter classification in Persian poetries using support vector machines , 2009, 2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[13]  Frank K. Soong,et al.  DNN i-Vector Speaker Verification with Short, Text-Constrained Test Utterances , 2017, INTERSPEECH.

[14]  C. V. Jawahar,et al.  On Using Classical Poetry Structure for Indian Language Post-Processing , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[15]  Yen-Chi Chen,et al.  A tutorial on kernel density estimation and recent advances , 2017, 1704.03924.

[16]  Rodolfo Delmonte,et al.  A Computational Approach to Poetic Structure, Rhythm and Rhyme , 2014 .

[17]  H. Tizhoosh,et al.  Poetic Features for Poem Recognition: A Comparative Study , 2008 .

[18]  Patrick Kenny,et al.  Front-End Factor Analysis for Speaker Verification , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[19]  Shahrul Azman Mohd Noah,et al.  Poetry Classification Using Support Vector Machines , 2012 .

[20]  Rajeev Rajan,et al.  Deep Neural Network Based Poetic Meter Classification Using Musical Texture Feature Fusion , 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

[21]  Gerald Friedland,et al.  An i-Vector Representation of Acoustic Environments for Audio-Based Video Event Detection on User Generated Content , 2013, 2013 IEEE International Symposium on Multimedia.

[22]  George E. Dahl.  Deep Learning Approaches to Problems in Speech Recognition, Computational Chemistry, and Natural Language Text Processing , 2015 .

[23]  Gholamreza Haffari,et al.  Automated Analysis of Bangla Poetry for Classification and Poet Identification , 2015, ICON.